© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 306
    Prev
    Next
    INDEX
    Explanations

    questions and conditional phrases related to decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.55
    Xna
    -0.49
    CopyWith
    -0.47
    /***/
    -0.43
    zarchiwizowane
    -0.43
    ICEF
    -0.42
    entid
    -0.42
    RTLR
    -0.41
    chables
    -0.40
    Życiorys
    -0.40
    POSITIVE LOGITS
     yes
    4.06
     Yes
    3.47
    Yes
    3.38
    yes
    3.25
     YES
    3.17
    YES
    2.83
     yeah
    2.27
     yep
    2.27
     sì
    2.13
     Yep
    2.09
    Activations Density 0.941%

    No Known Activations